scrapy爬取红袖添香并存入mysql

原创

微笑@鼠 2022-09-22 18:47:15 博主文章分类：Python ©著作权

文章标签 ide html mysql 文章分类 虚拟化云计算

©著作权归作者所有：来自51CTO博客作者微笑@鼠的原创作品，请联系作者获取转载授权，否则将追究法律责任

使用终端创建项目命令: scrapy startproject hongxiu

然后进入项目命令:cd hongxiu

接着创建爬取的项目名字和网址,命令:scrapy genspider hongxiu hongxiu.com

运行:scrapy ceawl hongxiu

hongxiu.py

# -*- coding: utf-8 -*-
import scrapy
from .. items import HongxiuItem

class XiuSpider(scrapy.Spider):
    def __init__(self):
        self.pageNum = 1
    name = 'xiu'
    allowed_domains = ['hongxiu.com']
    start_urls = ["https://www.hongxiu.com/finish"]

    def parse(self, response):
        print("开始爬行")
        div_list = response.xpath('//div[@class="right-book-list"]/ul/li')
        for div in div_list:
            title = div.xpath(".//div[@class='book-info']/h3/a/@title").extract_first()
            href = 'http://www.hongxiu.com' + div.xpath(".//div[@class='book-info']/h3/a/@href").extract_first()
            auth = div.xpath(".//div[@class='book-info']/h4/a/text()").extract_first()
            type = div.xpath(".//div[@class='book-info']/p/span/text()").extract_first()
            state = div.xpath(".//div[@class='book-info']/p/span[2]/text()").extract_first()
            count = div.xpath(".//div[@class='book-info']/p/span[3]/text()").extract_first()
            intro_li = div.xpath("normalize-space(.//div[@class='book-info']/p/text())").extract_first()
            cover_img = 'http:' + div.xpath(".//div[@class='book-img']/a//img/@src").extract_first()

            item = HongxiuItem()
            item['title'] = title
            item['auth'] = auth
            item['type'] = type
            item['state'] = state
            item['state'] = state
            item['count'] = count
            item['href'] = href
            item['intro_li'] = intro_li
            item['cover_img'] = [cover_img]

            yield item
        self.pageNum += 1
        next_url = "https://www.hongxiu.com/finish?pageSize=10&gender=2&catId=-1&isFinish=1&isVip=-1&size=-1&updT=-1&orderBy=0&pageNum=" + str(self.pageNum)
        print(next_url)
        yield scrapy.Request(url=next_url, callback=self.parse)

item.py

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class HongxiuItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    auth = scrapy.Field()
    type = scrapy.Field()
    state = scrapy.Field()
    count = scrapy.Field()
    href = scrapy.Field()
    intro_li = scrapy.Field()
    cover_img = scrapy.Field()
    pass

pipelines.py

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymysql


class HongxiuPipeline(object):
    def __init__(self):
        self.connect = pymysql.connect(host='localhost', user='root', password='123456', db='fiction', port=3306,
                                       charset='utf8mb4')
        self.cursor = self.connect.cursor()

    def process_item(self, item, spider):
        # self.connect.cursor()
        self.cursor.execute("INSERT INTO wd(title,auth,type,state,count,href,intro_li) VALUES('{}','{}','{}','{}','{}','{}','{}')".format(item['title'], item['auth'], item['type'],
                                                                           item['state'], item['count'], item['href'],
                                                                           item['intro_li']))
        self.connect.commit()
        return item

    def close_spider(self, spider):
        self.cursor.close()
        self.connect.close()

settings.py

# -*- coding: utf-8 -*-

# Scrapy settings for hongxiu project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'hongxiu'

SPIDER_MODULES = ['hongxiu.spiders']
NEWSPIDER_MODULE = 'hongxiu.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'hongxiu (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# 设置item时间延迟
# 250ms of delay
# DOWNLOAD_DELAY = 0.25
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'hongxiu.middlewares.HongxiuSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'hongxiu.middlewares.HongxiuDownloaderMiddleware': 543,
# }

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'hongxiu.pipelines.HongxiuPipeline': 300,
   'scrapy.pipelines.images.ImagesPipeline': 1

}
# 图片存储路径
IMAGES_STORE = "image"
IMAGES_URLS_FIELD = 'cover_img'


# mysql数据库的配置信息
MYSQL_HOST = '127.0.0.1'
# 数据库名字
MYSQL_DB = "fiction"
# 数据库账号
MYSQL_USER = 'root'
# 数据库密码
MYSQL_PASSWORD = '123456'
# 数据库端口号 ,在dbhelper中使用
MYSQL_PORT = 3306
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'